A novel approach for deterioration and damage identification in building structures based on Stockwell-Transform and deep convolutional neural network
Article
Article Title | A novel approach for deterioration and damage identification in building structures based on Stockwell-Transform and deep convolutional neural network |
---|---|
Article Category | Article |
Authors | Gharehbaghi, Vahid Reza, Kalbkhani, Hashem, Farsangi, Ehsan Noroozinejad, Yang, T.Y., Nguyen, Andy, Mirjalili, Seyedali and Malaga‑Chuquitaype, Christian |
Journal Title | Journal of Structural Integrity and Maintenance |
Journal Citation | 7 (2), pp. 136-150 |
Number of Pages | 15 |
Year | 2022 |
Publisher | Taylor & Francis |
Place of Publication | United Kingdom |
ISSN | 2470-5314 |
2470-5322 | |
Digital Object Identifier (DOI) | https://doi.org/10.1080/24705314.2021.2018840 |
Web Address (URL) | https://www.tandfonline.com/doi/full/10.1080/24705314.2021.2018840 |
Abstract | In this paper, a novel deterioration and damage identification procedure (DIP) is presented and applied to building models. The challenge associated with applications on these types of structures is related to the strong correlation of responses, an issue that gets further complicated when coping with real ambient vibrations with high levels of noise. Thus, a DIP is designed utilizing low-cost ambient vibrations to analyze the acceleration responses using the Stockwell transform (ST) to generate spectrograms. Subsequently, the ST outputs become the input of two series of Convolutional Neural Networks (CNNs) established for identifying deterioration and damage on the building models. To the best of our knowledge, this is the first time that both damage and deterioration are evaluated on building models through a combination of ST and CNN with high accuracy. |
Keywords | Deterioration; CNN; damage; Stockwell Transform; convolutional neural networks; deep learning |
ANZSRC Field of Research 2020 | 4005. Civil engineering |
Public Notes | File reproduced in accordance with the copyright policy of the publisher/author. |
Byline Affiliations | University of Southern Queensland |
Urmia University of Technology, Iran | |
Graduate University of Advanced Technology, Iran | |
University of British Columbia, Canada | |
Torrens University | |
Imperial College London, United Kingdom |
https://research.usq.edu.au/item/z01z9/a-novel-approach-for-deterioration-and-damage-identification-in-building-structures-based-on-stockwell-transform-and-deep-convolutional-neural-network
Download files
33
total views67
total downloads0
views this month0
downloads this month